CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

biome-code-review

Use only for reviewing completed Biome PRs, branches, commit ranges, diffs, or working trees against business logic and requirements. Excludes broad code-quality and process audits, triage, reproduction, and implementation.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exceptionally well-crafted instruction-only skill: lean imperative prose, concrete commands and templates, a clearly sequenced review workflow with validation and feedback loops, and a clean one-level reference structure with an explicit routing table. No significant weaknesses were found against any dimension.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of concept explanations or padding; rules like "Read every changed file in full" and "Stop tracing once the question is settled" assume competence. Restatements of reachability/totality rules across Review Method and Parent Validation serve distinct actors rather than padding, so it matches anchor 5 (lean, every token earns its place), not 4 where trimming would be needed.

5 / 5

Actionability

Concrete, executable guidance throughout: a literal shell allowlist (e.g., `git --no-pager diff --no-ext-diff --no-textconv ...`), a question-to-file routing table, exact severity definitions, and a copy-paste report template with `<severity>/<area>` tokens. For an instruction-only skill this matches anchor 5; parameter placeholders like `<number>` are appropriate inputs, not pseudocode.

5 / 5

Workflow Clarity

A clearly sequenced multi-step process (Establish Scope 1-5, two-pass Review Method, Parent Validation 1-5) with explicit validation checkpoints and feedback loops: the fetch-failure fallback ("continue with the local remote-tracking branch and disclose that it may be stale") and the validate/disprove/dispose loop. The skill is read-only, so the destructive/batch cap does not apply; this matches anchor 5.

5 / 5

Progressive Disclosure

The body serves as overview and process, while all four referenced files (repository-and-subsystems.md, workspace-access.md, rust-safety-and-syntax.md, documentation-and-process.md) exist and are one level deep; the routing table explicitly signals when to "Load" each, and the linked anchor `rust-safety-and-syntax.md#partial-operations` is real. This matches anchor 5 (well-signaled one-level-deep references, easy navigation).

5 / 5

Total

20

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, tight description: it names a specific niche, gives concrete trigger objects, and delimits scope with explicit exclusions. The only gaps are a few natural synonyms (e.g., "pull request", "code review") and the description of the review actions themselves.

DimensionReasoningScore

Specificity

The single action "reviewing" is applied to a comprehensive, concrete set of targets ("completed Biome PRs, branches, commit ranges, diffs, or working trees") checked "against business logic and requirements", with explicit exclusions. This matches anchor 4 (several specifics, minor gaps) rather than 5, which expects multiple distinct actions like extract/fill/merge.

4 / 5

Completeness

The explicit trigger clause "Use only for reviewing completed Biome PRs, branches, commit ranges, diffs, or working trees" answers when, and "reviewing ... against business logic and requirements" plus the exclusions clearly answer what. Both are explicit with concrete trigger phrases, matching anchor 5 rather than 4 where the when would be less specific.

5 / 5

Trigger Term Quality

"reviewing", "PRs", "branches", "diffs", and "working trees" are natural terms a user would say when requesting this skill. It falls short of anchor 5 because common synonyms such as "pull request" or "code review" are absent.

4 / 5

Distinctiveness Conflict Risk

"Biome" pins a clear niche and "Excludes broad code-quality and process audits, triage, reproduction, and implementation" actively prevents overlap with generic review skills. Clear niche with distinct triggers and minimal conflict risk, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

biomejs/biome

Path

.agents/skills/biome-code-review/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.